Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.1434. Min Act: -0.1700
Data Index: 8045623 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0496. Min Act: -0.1699
Data Index: 8178460 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0809. Min Act: -0.1700
Data Index: 2841540 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0809. Min Act: -0.1700
Data Index: 1269547 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0809. Min Act: -0.1700
Data Index: 6954910 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0809. Min Act: -0.1700
Data Index: 2553227 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0496. Min Act: -0.1700
Data Index: 6987577 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0496. Min Act: -0.1700
Data Index: 1521117 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0496. Min Act: -0.1700
Data Index: 7555585 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0184. Min Act: -0.1700
Data Index: 7299083 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0184. Min Act: -0.1700
Data Index: 4891859 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0496. Min Act: -0.1700
Data Index: 5587587 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0184. Min Act: -0.1700
Data Index: 1827521 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1434. Min Range: -5.1434
Max Act: 4.9871. Min Act: -0.1700
Data Index: 2509331 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1434. Min Range: -5.1434
Max Act: 4.9871. Min Act: -0.1700
Data Index: 7738542 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1434. Min Range: -5.1434
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3407301 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1434. Min Range: -5.1434
Max Act: 5.0184. Min Act: -0.1700
Data Index: 7431249 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1434. Min Range: -5.1434
Max Act: 4.9871. Min Act: -0.1700
Data Index: 714524 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1434. Min Range: -5.1434
Max Act: 4.9871. Min Act: -0.1700
Data Index: 8752946 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1434. Min Range: -5.1434
Max Act: 4.9559. Min Act: -0.1700
Data Index: 5305669 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19